CN117450023A - Fan vibration online diagnosis method and system based on generalized extremum distribution - Google Patents
Fan vibration online diagnosis method and system based on generalized extremum distribution Download PDFInfo
- Publication number
- CN117450023A CN117450023A CN202311249544.7A CN202311249544A CN117450023A CN 117450023 A CN117450023 A CN 117450023A CN 202311249544 A CN202311249544 A CN 202311249544A CN 117450023 A CN117450023 A CN 117450023A
- Authority
- CN
- China
- Prior art keywords
- vibration
- fan
- probability density
- data
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003745 diagnosis Methods 0.000 title claims abstract description 27
- 230000001186 cumulative effect Effects 0.000 claims description 59
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 4
- 101100324465 Caenorhabditis elegans arr-1 gene Proteins 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
- G01H1/003—Measuring characteristics of vibrations in solids by using direct conduction to the detector of rotating machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/80—Diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/84—Modelling or simulation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/334—Vibration measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Sustainable Energy (AREA)
- Sustainable Development (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fan vibration online diagnosis method and system based on generalized extremum distribution, the method filters, extracts characteristic values and calculates fitting distribution conditions through old historical vibration time sequence data to obtain a generalized extremum distribution curve of a fan, calculates an accumulated probability density curve of the curve, namely a fitting model, calculates critical point extremum data according to the curve, enables a fan main control to directly judge the theoretical occurrence probability of the vibration condition at the moment according to the condition of the fitting model, and flexibly adjusts a control strategy according to the probability, so as to achieve the effect of real-time vibration online diagnosis; the invention has simple implementation and low cost, does not need to additionally add other equipment on the original basis, does not need facilities such as the Internet and the like, only needs to modify the main control program code of the fan, has simple and clear bottom logic, and is convenient for debugging and modifying the corresponding operation logic of the main control.
Description
Technical Field
The invention relates to the technical field of fan online detection, in particular to a fan vibration online diagnosis method and system based on generalized extremum distribution.
Background
At present, the fan is generally provided with a vibration sensor and a collector which can collect vibration, so that the vibration of each part of the fan can be collected in real time and recorded and stored. The vibration acquisition system is used as an auxiliary control system and is independent of a main control system of the fan.
Vibration time sequence data can be periodically acquired by the vibration detection system at intervals, characteristic values such as effective values are calculated and uploaded to the fan main control system. The main control of the fan can simply and roughly formulate an alarm limit value and a shutdown limit value according to the limit value, and when the alarm limit value and the shutdown limit value are exceeded, the fan can be shut down to ensure safety.
However, with simple limit partitioning, the following problems can occur: firstly, the limit value is only divided manually, is not strict and scientific, and cannot adapt to different types of fans; secondly, the field environment of the wind field is complex, signal interference exists, and the acquired vibration value is larger than the actual vibration value, so that error shutdown is triggered; thirdly, by adopting a simple limit value method, only the vibration condition can be qualitatively analyzed, quantitative analysis can not be performed, and the control strategy can not be flexibly adjusted according to the vibration value.
In order to avoid the problems, the prior art extracts the collected vibration signals through a machine learning algorithm, adopts a supervised learning algorithm, trains a neural network model in advance, is arranged on a special server of a fan, outputs a result through the neural network model, and judges whether shutdown is needed; however, the method requires higher calculation force, requires additional arrangement of servers, and increases cost; and machine learning belongs to a black box, so that engineers cannot judge the internal rationality of each output result, and the main control program code is difficult to flexibly adjust according to the output result.
In addition, the data are firstly transmitted back to the cloud server through the network, the vibration judgment result is uniformly calculated through the cloud server, and then the result is returned to the fan main control system; however, when the number of wind field fans is large, the real-time performance is insufficient, the flow bandwidth requirement is large, and the offshore wind turbines have no network signals and the like.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a fan vibration online diagnosis method and system based on generalized extremum distribution, which are used for obtaining a generalized extremum distribution curve of a fan by filtering and extracting characteristic values and fitting distribution conditions through old historical vibration data, wherein the occurrence probability of a vibration condition theory at the moment can be directly judged by a fan master control through an accumulated probability density curve of the curve, the condition can be quantified, and a control strategy can be flexibly adjusted according to a model.
The aim of the invention is achieved by the following technical scheme: a fan vibration online diagnosis method based on generalized extremum distribution comprises the following steps:
s1, classifying according to preset conditions, acquiring historical vibration time sequence data of each measuring point of a plurality of fans, and eliminating abnormal data in the historical vibration time sequence data;
s2, filtering the acquired historical vibration time sequence data to eliminate interference;
s3, extracting and calculating characteristic values of the filtered time sequence data;
s4, uniformly distributing and extracting the characteristic value data of the fans obtained by calculation in the step S3, wherein the extraction number is larger than the original sample number, and a matrix is formed to ensure that the data weights of the fans are equal;
s5, fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition, and obtaining parameters describing the cumulative probability density curve to obtain a fitting model;
s6, calculating the critical point polar value data according to the cumulative probability density curve of the generalized extreme value distribution;
s7, writing related parameters of generalized extremum distribution into a fan main control program, and calculating a corresponding cumulative probability density value by the fan main control program according to the actually measured vibration time sequence characteristic value;
s8, diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value by the fan main control program, and executing operation corresponding to the vibration condition on the fan.
Further, the step S1 includes the steps of:
according to the vicinity of the rated wind speed interval, historical vibration time sequence data of each measuring point of a plurality of fans of the same model are obtained, and abnormal historical vibration data are deleted; the historical vibration time sequence data comprise acceleration, speed and displacement, and the measuring points comprise a main bearing, a gear box, a generator and a cabin tower of the fan.
Further, the step S2 includes the steps of:
filtering the acquired historical vibration time sequence data in a preset frequency band to remove data of other frequencies; wherein the frequency band comprises 0.1-10Hz, 10-1000Hz and 10-2000Hz.
Further, the step S3 includes the steps of:
extracting and calculating characteristic values of the filtered time sequence data to obtain characteristic value data of each fan; wherein the characteristic values include root mean square values, peak-to-peak values, and kurtosis.
Further, the step S4 includes the steps of:
uniformly distributing and extracting the characteristic value data of fans with the same type but different numbers, wherein the extraction number is larger than the original sample number, so as to form a matrix, and each column of the matrix is the characteristic value after the extraction is uniformly distributed for the corresponding fan; meanwhile, the weight of each fan is required to be consistent, namely the input sample number of each fan is required to be consistent.
Further, the step S5 includes the steps of:
after all vibration time sequence data of the fans of the same model are extracted with characteristics, fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition of the vibration time sequence data, and obtaining three parameters describing the cumulative probability density curve, including a position parameter mu, a scale parameter sigma and a shape parameter k, wherein the cumulative probability density function of the generalized extremum distribution is defined as:
where x is a sample value, exp () is an exponential function based on a natural constant e, μ is a position parameter of the cumulative probability density curve, σ is a scale parameter of the cumulative probability density curve, and k is a shape parameter of the cumulative probability density curve.
Further, the step S6 includes the steps of:
calculating the critical point polar value data according to the cumulative probability density curve of the generalized extreme value distribution; the key point polar data includes 75% quantile, 95% quantile, 99.7% quantile and quarter pitch.
Further, the step S7 includes the steps of:
writing related parameters of the generalized extremum distribution into a main control program of the fan, substituting a generalized extremum distribution formula according to the actually measured vibration time sequence characteristic value x of the fan, and calculating a cumulative probability density value corresponding to the vibration characteristic value by the main control programWhere exp () is an exponential function based on a natural constant e, μ is a position parameter of the cumulative probability density curve, σ is a scale parameter of the cumulative probability density curve, and k is a shape parameter of the cumulative probability density curve.
Further, the step S8 includes the steps of:
according to the accumulated probability density value y, the main control program controls the fan to perform corresponding operation; if the cumulative probability density of the corresponding vibration characteristic value is smaller than 75% quantile of the generalized extremum distribution fitting model, namely y is smaller than or equal to p75, the vibration is considered to be in a normal condition and is operated normally; if y is greater than p75 and y is less than or equal to p95, indicating that the vibration value is relatively larger, and recording reminding is needed without stopping; if y > p99, indicating that the vibration value is larger, immediately acquiring the latest vibration data again, calculating a new y value, avoiding false triggering, and if the accumulated probability density value corresponding to the new characteristic value is y > p99, adopting power-down operation until the y value meets the requirement; if y > p75+1.5Xp_iqr, the vibration is very intense, the latest vibration data is collected again, and if the vibration data is still in the interval, a shutdown strategy is adopted to ensure the safe operation of the fan.
An online fan vibration diagnosis system based on generalized extremum distribution is used for realizing the online fan vibration diagnosis method based on generalized extremum distribution, and the system comprises the following components:
the data acquisition module is used for acquiring historical vibration time sequence data of each measuring point of the fans and eliminating abnormal data in the historical vibration time sequence data;
the data filtering module is used for filtering the acquired historical vibration time sequence data and eliminating interference;
the characteristic value extraction module is used for extracting and calculating the characteristic value of the filtered time sequence data;
the uniform distribution extraction module is used for uniformly distributing and extracting the characteristic value data of the fans obtained through calculation to form a matrix;
the fitting model construction module is used for fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition, obtaining parameters describing the cumulative probability density curve and obtaining a fitting model;
the key point extreme value data calculation module calculates key point extreme value data according to the cumulative probability density curve of the generalized extreme value distribution;
the cumulative probability density value calculation module calculates a corresponding cumulative probability density value according to the actually measured vibration time sequence characteristic value;
and the diagnosis module is used for diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value and executing the operation corresponding to the vibration condition on the fan.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. according to the invention, characteristic values are extracted through filtering of past historical vibration data, a distribution condition is fitted, and a generalized extremum distribution curve of the fan is obtained, wherein the generalized extremum distribution has three undetermined parameters, the generalized extremum distribution has higher adaptability than other 2-parameter models, meanwhile, the modeling analysis effect of the fitting model on extreme variability is better, so that the modeling fitting effect on the extreme vibration value is better, and the fan main control can flexibly adjust a control strategy according to the model through an accumulated probability density curve of the curve.
2. The invention has simple implementation and low cost, does not need to additionally add other equipment on the original basis, does not need facilities such as the Internet and the like, and only needs to modify the main control program code of the fan.
3. The invention has simple logic at the bottom layer, and is convenient for debugging and modifying the operation logic corresponding to the main control.
Drawings
FIG. 1 is a flow chart of a fan vibration on-line diagnostic method.
FIG. 2 is a flow chart for on-line diagnostics of A-type fan vibrations.
Fig. 3 is a graph of probability density for a fitted model.
FIG. 4 is a graph of cumulative probability density for a generalized extremum distribution.
Detailed Description
The invention will be further illustrated with reference to specific examples.
Example 1
Referring to fig. 1 to 4, the fan vibration online diagnosis method based on generalized extremum distribution provided by the embodiment includes the following steps:
s1, classifying according to preset conditions, acquiring historical vibration time sequence data of each measuring point of a plurality of fans, and eliminating abnormal data in the historical vibration time sequence data, wherein the method comprises the following steps of:
according to the rated wind speed interval, acquiring a front bearing measuring point of a generator of the A-type fan, deleting historical vibration data of abnormal data, and acquiring vibration time sequences data_1, data_2 and data_3 … … data_n; in addition, the vibration time sequence comprises physical quantities such as acceleration, speed or displacement, and the measuring points comprise a main bearing, a gear box, a generator and a nacelle tower.
S2, filtering the acquired historical vibration time sequence data to remove interference, wherein the method comprises the following steps of:
performing 10 to 5000Hz band-pass filtering on the historical vibration data of the generator to obtain filtered time sequence data fdata_1, fdata_2 and fdata_3 … … fdata_n; each measuring point filtering frequency section comprises: 0.1 to 10Hz, 10 to 1000Hz, and 10 to 2000Hz.
S3, extracting and calculating characteristic values of the filtered time sequence data, wherein the method comprises the following steps of:
and calculating the characteristic value of the filtering data to obtain a characteristic value array of each unit, wherein the characteristic value of the example is a root mean square value. By adopting the method, a plurality of root mean square value arrays of the same type of fans are obtained, for example, the fan 1 is arr_1= [ rms1, rms2, rms3 … … rms_n ], the fan 2 is arr_2, and the fan n is arr_n. The characteristic values include root mean square values, peak-to-peak values, and kurtosis.
S4, uniformly distributing and extracting the characteristic value data of a plurality of fans calculated in the step S3, wherein the extraction number is larger than the original sample number, and a matrix is formed to ensure that the data weights of the fans are equal, and the method comprises the following steps:
and uniformly distributing and extracting the characteristic value arrays of the fans, wherein the extraction number is n_samp, and n_samp is greater than the maximum length of the root mean square array, so as to obtain a data matrix with equal weight, and each row of the matrix is the characteristic value after the corresponding fans are uniformly distributed and extracted. For example, if the maximum length of the arr array is 100, the sampling number n_smap=500. 500 pieces of arr1 root mean square data are extracted uniformly distributed and placed in the first column of matrix. 500 pieces of arr_n root mean square data are also uniformly extracted and placed in the nth column of the matrix.
The code is as follows:
idx＝randi([1,length(arr_n)],n_samp,1)；
matrix(:,n)＝arr_n(idx)；
s5, fitting a cumulative probability density curve of generalized extremum distribution according to distribution conditions to obtain parameters describing the cumulative probability density curve and obtain a fitting model, wherein the method comprises the following steps of:
fitting all data of the matrix as a whole sample to obtain three parameters of a generalized extremum distribution object pd and a curve: position parameter μ, scale parameter σ, shape parameter k;
the code is as follows: pd=fitdst (matrix (:), 'Generalized Extreme Value').
S6, calculating extreme value data of the key points according to an accumulated probability density curve of generalized extreme value distribution, wherein the method comprises the following steps of:
calculating key point limit value data: calculating 75% quantiles, 95% quantiles, 99.7 quantiles and the like; using the function p_75=prctile (pd, 75), p_95=prctile (pd, 95), p_99=prctile (pd, 99.7); the quarter pitch p_iqr=iqr (pd) is calculated.
S7, writing related parameters of generalized extremum distribution into a fan main control program, and calculating a corresponding cumulative probability density value by the fan main control program according to the actually measured vibration time sequence characteristic value, wherein the method comprises the following steps of:
writing the relevant parameters into a main control program, substituting a generalized extremum distribution formula according to the actually measured vibration time sequence characteristic value x, and calculating a cumulative probability density value corresponding to the vibration characteristic value by the main control program
S8, diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value by the fan main control program, and executing the operation corresponding to the vibration condition on the fan, wherein the method comprises the following steps of:
according to the accumulated probability density value y, the main control program controls the fan to perform corresponding operation; if the cumulative probability density of the corresponding vibration characteristic value is smaller than 75% quantile of the generalized extremum distribution fitting model, namely y is smaller than or equal to p75, the vibration is considered to be in a normal condition and is operated normally; if y is greater than p75 and y is less than or equal to p95, indicating that the vibration value is relatively larger, and recording reminding is needed without stopping; if y > p99, indicating that the vibration value is larger, immediately acquiring the latest vibration data again, calculating a new y value, avoiding false triggering, and if the accumulated probability density value corresponding to the new characteristic value is y > p99, adopting power-down operation until the y value meets the requirement; if y > p75+1.5Xp_iqr, the vibration is very intense, the latest vibration data is collected again, and if the vibration data is still in the interval, a shutdown strategy is adopted to ensure the safe operation of the fan.
Example 2
The embodiment discloses a fan vibration online diagnosis system based on generalized extremum distribution, which is used for realizing the fan vibration online diagnosis method based on generalized extremum distribution described in embodiment 1, and comprises the following steps:
the data acquisition module is used for acquiring historical vibration time sequence data of each measuring point of the fans and eliminating abnormal data in the historical vibration time sequence data;
the data filtering module is used for filtering the acquired historical vibration time sequence data and eliminating interference;
the characteristic value extraction module is used for extracting and calculating the characteristic value of the filtered time sequence data;
the uniform distribution extraction module is used for uniformly distributing and extracting the characteristic value data of the fans obtained through calculation to form a matrix;
the fitting model construction module is used for fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition, obtaining parameters describing the cumulative probability density curve and obtaining a fitting model;
the key point extreme value data calculation module calculates key point extreme value data according to the cumulative probability density curve of the generalized extreme value distribution;
the cumulative probability density value calculation module calculates a corresponding cumulative probability density value according to the actually measured vibration time sequence characteristic value;
and the diagnosis module is used for diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value and executing the operation corresponding to the vibration condition on the fan.
Example 3
The present embodiment discloses a non-transitory computer readable medium storing instructions which, when executed by a processor, perform the steps of the fan vibration online diagnostic method based on generalized extremum distribution according to embodiment 1.
The non-transitory computer readable medium in this embodiment may be a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a usb disk, a removable hard disk, or the like.
Example 4
The embodiment discloses a computing device, which comprises a processor and a memory for storing a program executable by the processor, wherein when the processor executes the program stored by the memory, the fan vibration online diagnosis method based on generalized extremum distribution described in the embodiment 1 is realized.
The computing device described in this embodiment may be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, a tablet computer, a programmable logic controller (PLC, programmable Logic Controller), or other terminal devices with processor functionality.
The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, so variations in shape and principles of the present invention should be covered.
Claims (10)
1. The fan vibration online diagnosis method based on generalized extremum distribution is characterized by comprising the following steps of:
s1, classifying according to preset conditions, acquiring historical vibration time sequence data of each measuring point of a plurality of fans, and eliminating abnormal data in the historical vibration time sequence data;
s2, filtering the acquired historical vibration time sequence data to eliminate interference;
s3, extracting and calculating characteristic values of the filtered time sequence data;
s4, uniformly distributing and extracting the characteristic value data of the fans obtained by calculation in the step S3, wherein the extraction number is larger than the original sample number, and a matrix is formed to ensure that the data weights of the fans are equal;
s5, fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition, and obtaining parameters describing the cumulative probability density curve to obtain a fitting model;
s6, calculating the critical point polar value data according to the cumulative probability density curve of the generalized extreme value distribution;
s7, writing related parameters of generalized extremum distribution into a fan main control program, and calculating a corresponding cumulative probability density value by the fan main control program according to the actually measured vibration time sequence characteristic value;
s8, diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value by the fan main control program, and executing operation corresponding to the vibration condition on the fan.
2. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S1 comprises the steps of:
according to the vicinity of the rated wind speed interval, historical vibration time sequence data of each measuring point of a plurality of fans of the same model are obtained, and abnormal historical vibration data are deleted; the historical vibration time sequence data comprise acceleration, speed and displacement, and the measuring points comprise a main bearing, a gear box, a generator and a cabin tower of the fan.
3. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S2 comprises the steps of:
filtering the acquired historical vibration time sequence data in a preset frequency band to remove data of other frequencies; wherein the frequency band comprises 0.1-10Hz, 10-1000Hz and 10-2000Hz.
4. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S3 comprises the steps of:
extracting and calculating characteristic values of the filtered time sequence data to obtain characteristic value data of each fan; wherein the characteristic values include root mean square values, peak-to-peak values, and kurtosis.
5. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S4 comprises the steps of:
uniformly distributing and extracting the characteristic value data of fans with the same type but different numbers, wherein the extraction number is larger than the original sample number, so as to form a matrix, and each column of the matrix is the characteristic value after the extraction is uniformly distributed for the corresponding fan; meanwhile, the weight of each fan is required to be consistent, namely the input sample number of each fan is required to be consistent.
6. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S5 comprises the steps of:
after all vibration time sequence data of the fans of the same model are extracted with characteristics, fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition of the vibration time sequence data, and obtaining three parameters describing the cumulative probability density curve, including a position parameter mu, a scale parameter sigma and a shape parameter k, wherein the cumulative probability density function of the generalized extremum distribution is defined as:
where x is a sample value, exp () is an exponential function based on a natural constant e, μ is a position parameter of the cumulative probability density curve, σ is a scale parameter of the cumulative probability density curve, and k is a shape parameter of the cumulative probability density curve.
7. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S6 comprises the steps of:
calculating the critical point polar value data according to the cumulative probability density curve of the generalized extreme value distribution; the key point polar data includes 75% quantile, 95% quantile, 99.7% quantile and quarter pitch.
8. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S7 comprises the steps of:
writing related parameters of the generalized extremum distribution into a main control program of the fan, substituting a generalized extremum distribution formula according to the actually measured vibration time sequence characteristic value x of the fan, and calculating a cumulative probability density value corresponding to the vibration characteristic value by the main control programWhere exp () is an exponential function based on a natural constant e, μ is a position parameter of the cumulative probability density curve, σ is a scale parameter of the cumulative probability density curve, and k is a shape parameter of the cumulative probability density curve.
9. The method for online diagnosis of fan vibration based on generalized extremum distribution according to claim 1, wherein the step S8 comprises the steps of:
according to the accumulated probability density value y, the main control program controls the fan to perform corresponding operation; if the cumulative probability density of the corresponding vibration characteristic value is smaller than 75% quantile of the generalized extremum distribution fitting model, namely y is smaller than or equal to p75, the vibration is considered to be in a normal condition and is operated normally; if y is greater than p75 and y is less than or equal to p95, indicating that the vibration value is relatively larger, and recording reminding is needed without stopping; if y > p99, indicating that the vibration value is larger, immediately acquiring the latest vibration data again, calculating a new y value, avoiding false triggering, and if the accumulated probability density value corresponding to the new characteristic value is y > p99, adopting power-down operation until the y value meets the requirement; if y > p75+1.5Xp_iqr, the vibration is very intense, the latest vibration data is collected again, and if the vibration data is still in the interval, a shutdown strategy is adopted to ensure the safe operation of the fan.
10. A fan vibration online diagnosis system based on generalized extremum distribution, which is used for realizing the fan vibration online diagnosis method based on generalized extremum distribution according to any one of claims 1-9, the system comprising:
the data acquisition module is used for acquiring historical vibration time sequence data of each measuring point of the fans and eliminating abnormal data in the historical vibration time sequence data;
the data filtering module is used for filtering the acquired historical vibration time sequence data and eliminating interference;
the characteristic value extraction module is used for extracting and calculating the characteristic value of the filtered time sequence data;
the uniform distribution extraction module is used for uniformly distributing and extracting the characteristic value data of the fans obtained through calculation to form a matrix;
the fitting model construction module is used for fitting a cumulative probability density curve of generalized extremum distribution according to the distribution condition, obtaining parameters describing the cumulative probability density curve and obtaining a fitting model;
the key point extreme value data calculation module calculates key point extreme value data according to the cumulative probability density curve of the generalized extreme value distribution;
the cumulative probability density value calculation module calculates a corresponding cumulative probability density value according to the actually measured vibration time sequence characteristic value;
and the diagnosis module is used for diagnosing the vibration condition of the fan according to the calculated corresponding cumulative probability density value and executing the operation corresponding to the vibration condition on the fan.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311249544.7A CN117450023A (en) | 2023-09-25 | 2023-09-25 | Fan vibration online diagnosis method and system based on generalized extremum distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311249544.7A CN117450023A (en) | 2023-09-25 | 2023-09-25 | Fan vibration online diagnosis method and system based on generalized extremum distribution |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117450023A true CN117450023A (en) | 2024-01-26 |
Family
ID=89591883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311249544.7A Pending CN117450023A (en) | 2023-09-25 | 2023-09-25 | Fan vibration online diagnosis method and system based on generalized extremum distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117450023A (en) |
-
2023
- 2023-09-25 CN CN202311249544.7A patent/CN117450023A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| Camci et al. | Feature evaluation for effective bearing prognostics | |
| JP5101396B2 (en) | Soundness diagnosis method and program, and windmill soundness diagnosis device | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| EP2172824B1 (en) | Method and system of wind turbine condition monitoring | |
| EP3947961B1 (en) | A method for estimating remaining useful life of components of an operational wind turbine | |
| EP3480455B1 (en) | Wind turbine monitoring device, wind turbine monitoring method, wind turbine monitoring program, and storage medium | |
| US8355879B2 (en) | Trending of vibration data taking into account torque effect | |
| CN111997831B (en) | Load control method and device of wind turbine generator | |
| DE102016117190A1 (en) | A method and apparatus for monitoring a condition of at least one wind turbine and computer program product | |
| CN116624343B (en) | Wind turbine generator tower abnormal vibration monitoring and health degree evaluation method and system | |
| CN116415126A (en) | Method, device and computing equipment for anomaly detection of doctor blades of paper machine | |
| EP3859147A1 (en) | Wake monitoring, wake management and sensory arrangements to such | |
| CN110488188B (en) | Unit three-dimensional health quantitative evaluation method based on dynamic threshold | |
| CN116105885A (en) | State monitoring method and system for electrical equipment for nuclear power | |
| CN112524077A (en) | Method, device and system for detecting fan fault | |
| CN117450023A (en) | Fan vibration online diagnosis method and system based on generalized extremum distribution | |
| CN116862109A (en) | Regional carbon emission situation awareness early warning method | |
| EP3869286A1 (en) | System and method for detecting turbine underperformance and operation anomaly | |
| CN117332360B (en) | Greenhouse equipment fault monitoring method and system based on 5G technology | |
| WO2022190972A1 (en) | State monitoring system | |
| CN116757087B (en) | State evaluation method and related equipment for offshore wind power support structure | |
| CN117707050B (en) | Cloud computing-based numerical control machine tool real-time monitoring and data analysis system and method | |
| CN116950855B (en) | Offshore wind power structure health state monitoring method and related equipment | |
| Wang et al. | Multi-machine Based Wind Turbine Gearbox Condition Monitoring Using Nonlinear State Estimation Technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |